Abstract
The agricultural sector is the backbone of the Indian economy, where precision agriculture is playing a vital role in boosting productivity. The soil chemical parameters play an important role in precision agriculture. Analysis and prediction of micronutrient of the soil chemical parameters are highly insisted upon by farmers and agriculture researchers. The soil nutrients parameters can be analyzed from multispectral data through ISO cluster unsupervised classification. Understanding the nutrient level of soil is highly recommended for farming; early understanding may help to improve soil fertility and fully meet productivity requirements. This paper addresses the soil nutrients analysis by the regression method and its spectral indexed based on the prediction model by Iterative Self-Organizing (ISO) cluster unsupervised classification algorithm. Therefore, for this study, the Baggi, Ibrahimpur, Wai, Mogra, and Bori (for validation) villages were selected. These villages are located in the Amravati district and fall under Maharashtra provenance of India. From the study area, three soil nutrients parameters such as P, Fe, pH indices-based data were acquired from the spectral calculation of Sentinel-2 and Landsat-8 bands. The P, Fe and pH indices were calculated from the yellowness index (YI), ferrous oxide index, and carbonate level. The ISO cluster unsupervised mechanism has been used for prediction of soil chemical parameter indices out of 100 samples. The study regions recognition rate is 97% for P, 94.05% for Fe, and 69% for pH. During the validation process, four villages' results were used for the identification of soil nutrient parameters for Bori village. The results of the study area can be helpful for the development of the planning of soil fertility in the agriculture fields and effectively increase the crop yield production in the semi-arid region.
Similar content being viewed by others
Abbreviations
- ISO:
-
Iterative Self-Organizing
- P:
-
Phosphorus
- Fe:
-
Ferric Oxide
- pH:
-
Potential of Hydrogen
- RS:
-
Remote Sensing
- GIS:
-
Geographic Information System
- GPS:
-
Global Positioning System
- EC:
-
Electrical Conductivity
- OC:
-
Organic Carbon Content
- MLP:
-
Machine Learning Programming
- NDVI:
-
Normalized Difference Vegetation Index
- YI:
-
Yellowness Index
References
Bach H, Mauser W (2003) Methods and examples for remote sensing data assimilation in land surface process modeling. IEEE Trans Geosci Remote Sens 41(7) Part: 1:1629–1637
Barnes EM, Sudduth KA, Hummel JW, Lesch SM, Corwin DL, Yang C, Daughtry CST, Bausch WC (2003) Remote- and ground-based sensor techniques to map soil properties. Ame Soc Photogramm Engin Remote Sens 69(6):619–630
Ben-Dor E, Banin A (1995) Near-infrared analysis as a rapid method to simultaneously evaluate several soil properties. Soil Sci Soc Am J 59(2):364–372
Chen H, Zhao G, Wang Y, Sui L, Meng H (2011) Discussion on remote sensing estimation of soil nutrient contents. In: International conference on remote sensing, environment and transportation engineering (RSETE), pp 3072–3075 2011
Dong H, Chen C, Wang J, Qin Q, Jiang H, Zhang N, Liu M (2011) Study on quantitative retrieval of soil nutrients. In: IEEE international geoscience and remote sensing symposium (IGARSS), pp 3330–3333
Forkuor G, Dimobe K, Serme I, Tondoh JE (2018) Landsat-8 vs. Sentinel-2: examining the added value of sentinel-2’s red-edge bands to landuse and land-cover mapping in Burkina Faso. GISci Remote Sensing 55(3):331–354. https://doi.org/10.1080/15481603.2017.1370169
Hank T, Bach H, Mauser W (2015) Using a remote sensing-supported hydro-Agroecological model for field-scale simulation of heterogeneous crop growth and yield: application for wheat in Central Europe. Remote Sens 7:3934–3965. https://doi.org/10.3390/rs70403934
Huang Y, Kuang X, Cao Y, Bai Z (2018) The soil chemical properties of reclaimed land in an arid grassland dump in an opencast mining area in China. RSC Adv 2018(8):41499
Ines AVM, Das NN, Hansen JW, Njoku EG (2013) Assimilation of remotely sensed soil moisture and vegetation with a crop simulation model for maize yield prediction. Remote Sens Environ 138:149–164 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5256943
Isenstein EM, Park M-H (2014) Assessment of nutrient distributions in Lake Champlain using satellite remote sensing. J Environ Sci 26(9):1831–1836
Kneubuhler M, Damm A, Schweiger AK, Risch AC, Schutz M, Schaepman ME (2014) Continuous fields from imaging spectrometer data for ecosystem parameter mapping and their potential for animal habitat assessment in Alpine regions. IEEE J Selected Top Appl Earth Observ Remote Sens 7(6):2600–2610
Kumar N, Velmurugan A, Hamm NAS, Dadhwal VK (2018) Geospatial mapping of soil organic carbon using regression kriging and remote sensing. J Indian Soc Remote Sens 2018 46(5):705–716
Liao Q, Wang J, Li C, Xiaohe G (2012) Estimation of fluvo-aquic soil organic matter from hyperspectral reflectance by using discrete wavelet transformation. In: IEEE-2012 first international conference on agro-Geoinformatics (agro-Geoinformatics), pp 1–5
Lihua X, Xie D (2012) Prediction for available nitrogen and available phosphorus by using hyperspectral data. In: 2nd international conference on remote sensing, environment and transportation engineering (RSETE), 1–3 June 2012
Lin Qiu, Xiaomin Chen and Jianjun Pan (2016) In situ measurement of soil macropores by dye tracing and image analysis. Second International Conference on Agro-Geoinformatics (Agro-Geoinformatics), IEEE, pp 13–17, Aug. 2013.
Moran MS, Inoue Y, Barnes EM (1997) Opportunities and limitations for image-based remote sensing in precision crop management. Remote Sens Environ 61:319–346
Mulla DJ (2013) Twenty five years of remote sensing in precision agriculture: key advances and remaining knowledge gaps. Biosyst Engin; Special Issue: Sens Agricult 114:358–371
Pande CB, Moharir KN, Khadri SFR, Patil S (2018) Study of land use classification in the arid region using multispectral satellite images. Appl Water Sci, Springer Journal 8(5):1–11
Peng L, Niu Z, Li L (2012) Prediction of soil organic carbon by hyperspectral remote sensing imagery. In: Third global congress on intelligent systems (GCIS), pp 291–293
Reddy DM, Patode RS, Nagdeve MB, Satpute GU, Pande CB (2017) Land use mapping of the Warkhed Micro-watershed with geo-spatial technology. Contemp Research India 7(3)
Tomar V, Mandal VP, Srivastava P, Patairiya S, Singh K, Ravisankar N, Subash N, Kumar P (2014) Rice equivalent crop yield assessment using MODIS sensors’ based MOD13A1-NDVI data. IEEE Sensors J 14(10):3599–3609
Ustin L, Asner GP, Gamon JA, Huemmrich KF, Jacquemoud S, Schaepman M, Zarco-Tejada P (2006) Retrieval of quantitative and qualitative information about plant pigment systems from high-resolution spectroscopy. In: IEEE international conference on geoscience and remote sensing symposium. IGARSS-2006, pp 1996–1999
Wang X, Mannaerts CM, Yang S, Gao Y, Zheng D (2010) Evaluation of soil nitrogen emissions from riparian zones coupling simple process-oriented models with remote sensing data. Sci Total Environ 408:3310–3318
Zhang X, Cao Y, Bai Z, Wang J, Zhou W, Ding X (2016) Relationships between vegetation coverage and soil properties on the reclaimed dump of opencast coal mine in loess plateau, China. Fresenius Environ Bull 25:4767–4776
Zheng H, Wu J, Shan Z (2009) Study on the spatial variability of farmland soil nutrient based on the kriging interpolation. Artificial intelligence and computational intelligence, AICI '09. In: International conference on vol. 4, pp 550–555
Conflict of interest
None.
Author information
Authors and Affiliations
Contributions
1. MLP processing of satellite and soil data.
2. Developed an algorithm based on four villages' soil and satellite data.
3. Validated four villages soil data and correlation with Bori village prdication results.
4. Developed model and algorithm; that can be helpfulful to pricesion farming and study of soil nutrients.
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Gulhane, V.A., Rode, S.V. & Pande, C.B. Correlation Analysis of Soil Nutrients and Prediction Model Through ISO Cluster Unsupervised Classification with Multispectral Data. Multimed Tools Appl 82, 2165–2184 (2023). https://doi.org/10.1007/s11042-022-13276-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-13276-2